# AI use cases for Modureader (sobranie2406/modureader) Repo: [sobranie2406/modureader](https://github.com/sobranie2406/modureader) | Use cases: 6 | Page: https://dedupedai.com/use-cases/sobranie2406-modureader/ Modu Reader (默读) is an open-source, cross-platform ebook and PDF reader built with Flutter, with scanned-book enhancement, on-device OCR, translation, read-aloud, notes and optional AI reading. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Read scanned PDFs with cleaner, larger pages: https://dedupedai.com/use-cases/sobranie2406-modureader/read-scanned-pdfs-with-auto-crop/ - Turn scanned pages into selectable text with on-device OCR: https://dedupedai.com/use-cases/sobranie2406-modureader/turn-scanned-pages-into-selectable-text/ - Read a foreign-language book with translation on each paragraph: https://dedupedai.com/use-cases/sobranie2406-modureader/read-a-foreign-book-side-by-side/ - Search a book by meaning with a local vector index: https://dedupedai.com/use-cases/sobranie2406-modureader/search-a-book-by-meaning-with-vector-index/ - Sync books, notes and reading progress to your own WebDAV server: https://dedupedai.com/use-cases/sobranie2406-modureader/sync-reading-progress-over-your-own-webdav/ - Look up words in your own offline dictionaries while reading: https://dedupedai.com/use-cases/sobranie2406-modureader/look-up-words-with-offline-dictionaries/ ## How to read scanned PDFs with cleaner, larger pages with Modureader Repo: [sobranie2406/modureader](https://github.com/sobranie2406/modureader) | Difficulty: Beginner | Time: 15 minutes | Basis: From the README Auto-crop margins and enhance scanned PDF pages in the reader, without changing the original file. **Who it is for:** A reader with scanned PDF or image-only books who finds the pages too small, too grey or full of wasted margins on a phone or e-ink screen. **The problem:** Scanned pages often have large blank borders, faint text and scan marks that make them hard to read on a small screen. **The outcome:** Pages show with trimmed margins, adjusted contrast and sharpening, while the original PDF stays unchanged. ### Steps 1. Install Modu Reader from the Releases page for your system and architecture. 2. Add the scanned PDF to the bookshelf and open it, or set an EPUB, MOBI, AZW3 or FB2 image book to the scanned-book view from the shelf menu. 3. Turn on automatic cropping and adjust the protected margin so page numbers, footnotes and text edges are kept. 4. Use the enhancement controls for text darkness, contrast, sharpening and bleach, and preview the result against the original page. 5. On e-ink devices, enable E-INK mode to show the refresh control, if your device supports it. ### Prompt to paste into your agent ```text Using the Modu Reader repo (sobranie2406/modureader), explain how to open with automatic cropping and enhancement enabled. Output the settings you changed and confirm that the original PDF file was not modified. ``` ### Caveat The README says scan watermark reduction cannot restore text hidden by a watermark, so check enhanced pages against the original scan. Dual-use notice: only use this on software, sites and systems you own or are authorized to test. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/sobranie2406-modureader/read-scanned-pdfs-with-auto-crop/ ## How to turn scanned pages into selectable text with on-device OCR with Modureader Repo: [sobranie2406/modureader](https://github.com/sobranie2406/modureader) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Download a small OCR model, re-flow scanned pages as text, then highlight, translate or ask AI about it. **Who it is for:** A reader with a scanned book or PDF who needs to copy passages, take notes or ask questions about pages that have no text layer. **The problem:** Image-only pages cannot be searched, copied or annotated, so the reader has to retype quotes by hand. **The outcome:** The page text opens in the reader with selection, highlights, notes and AI tools, and the recognition runs on the device. ### Steps 1. In 设置 → OCR 模型 (Settings → OCR model), choose PP-OCRv4 中英文 (the recommended model) and a download source, then download it. 2. If the device is offline, use the offline import option on the model card and import the full model file set for the matching version. 3. Open the PDF or scanned-book menu and choose OCR 重排 to recognize the page image, or 文字重排 if the PDF already has a text layer. 4. Select words in the re-flowed text to copy, translate, highlight or ask AI. 5. To send only part of a page to AI, use 提取 to choose a region, then review and edit the text in the AI input draft before sending. ### Prompt to paste into your agent ```text Using the sobranie2406/modureader repo, set up the PP-OCRv4 Chinese and English OCR model in Modu Reader and run OCR re-flow on . Report the model name, the pages processed, and one passage that you checked against the original scan. ``` ### Caveat The README says names, numbers and complex columns should be checked against the original page, because recognition depends on image clarity, language and layout. Dual-use notice: only use this on software, sites and systems you own or are authorized to test. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/sobranie2406-modureader/turn-scanned-pages-into-selectable-text/ ## How to read a foreign-language book with translation on each paragraph with Modureader Repo: [sobranie2406/modureader](https://github.com/sobranie2406/modureader) | Difficulty: Intermediate | Time: 15 minutes | Basis: From the README Show the original and translated text side by side on the reading page, or switch to translation only. **Who it is for:** A reader working through an ebook in a language they are still learning, who wants to check meaning paragraph by paragraph without leaving the page. **The problem:** Looking up one sentence at a time in a pop-up breaks reading flow, and a full book export is not practical. **The outcome:** The current reading area shows the translation inline, in 原文 + 译文 or 仅译文 mode. ### Steps 1. Open a book in the reader and open the translation panel. 2. Choose an engine: Google translate, AI translate, or DeepL / DeepLX. 3. Set the target language and choose 原文 + 译文 for side-by-side view or 仅译文 for translation only. 4. Read on. Translation loads with the reading position rather than exporting the whole book. 5. Use the stop control in the toolbar to end translation at any time. ### Prompt to paste into your agent ```text Using the Modu Reader repo (sobranie2406/modureader), configure whole-page translation for into in side-by-side mode. Report the engine chosen and confirm that the translation appears next to the original paragraph on the current page. ``` ### Caveat The README states that online translation sends the text to the selected provider, and local reading does not need any online service. Risk, credentials: Online engines such as DeepL, AI translation or a provider key send the text to be translated to the chosen service, so store keys only in the app settings you control. Dual-use notice: only use this on software, sites and systems you own or are authorized to test. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/sobranie2406-modureader/read-a-foreign-book-side-by-side/ ## How to search a book by meaning with a local vector index with Modureader Repo: [sobranie2406/modureader](https://github.com/sobranie2406/modureader) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Build a semantic index for one book so AI answers can pull the passages that match a question. **Who it is for:** A reader with a long nonfiction book who wants to find where an idea is discussed, even when the exact words differ. **The problem:** Keyword search misses passages that express the same idea in different words. **The outcome:** The book has a local index, and semantic search returns related original passages that can feed AI answers. ### Steps 1. Open 设置 → 向量模型 (Settings → vector model) and pick a local ONNX model, such as BGE Small ZH v1.5 for Chinese text, or a remote embedding API. 2. Download the model and tokenizer, or import the matching version offline, and wait for the size and SHA-256 check to pass. 3. Open the book's menu and build the index. 4. Check the background queue for progress until indexing finishes. 5. Run a semantic search and compare the results against the book text. ### Prompt to paste into your agent ```text Using the sobranie2406/modureader repo, configure the local BGE Small ZH v1.5 model in Modu Reader and build a vector index for . Report the indexing status, then list two results from a semantic query on and confirm each one appears in the book. ``` ### Caveat The README says the index stays on the device and is not synced by WebDAV, and changing the vector model requires rebuilding the index. Dual-use notice: only use this on software, sites and systems you own or are authorized to test. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/sobranie2406-modureader/search-a-book-by-meaning-with-vector-index/ ## How to sync books, notes and reading progress to your own WebDAV server with Modureader Repo: [sobranie2406/modureader](https://github.com/sobranie2406/modureader) | Difficulty: Advanced | Time: 45 minutes | Basis: From the README Keep reading progress, notes and bookmarks in step across devices, with a database backup before any restore. **Who it is for:** A reader with two or more devices and a WebDAV server they control, who wants notes and reading position to follow them. **The problem:** Reading position, notes and highlights stay on one device, so switching devices means losing place. **The outcome:** Books, notes, bookmarks, progress and per-book read-aloud positions are merged through WebDAV, and a ZIP backup is kept. ### Steps 1. Open 设置 → 同步 (Settings → Sync) and enter your WebDAV service details. 2. Turn on automatic sync and, if needed, the Wi-Fi-only option. 3. Export a database backup from 数据库备份 and keep the Modu-Backup-*.zip file somewhere safe. 4. Run sync on the second device using the same WebDAV service, and check that notes and progress match. 5. Before any restore, export a fresh backup, because restoring replaces the current data rather than merging it. ### Prompt to paste into your agent ```text Using the sobranie2406/modureader repo, configure WebDAV sync in Modu Reader on and export a database backup. Output the backup file name and confirm that the reading position for matches the other device after one sync. ``` ### Caveat The README says restoring a backup replaces existing data instead of merging, so back up the current library before restoring. Risk, credentials: WebDAV passwords and API keys are excluded from backups by default, and if you choose to include them the export is encrypted only when you set a password, so keep the backup file private. Dual-use notice: only use this on software, sites and systems you own or are authorized to test. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/sobranie2406-modureader/sync-reading-progress-over-your-own-webdav/ ## How to look up words in your own offline dictionaries while reading with Modureader Repo: [sobranie2406/modureader](https://github.com/sobranie2406/modureader) | Difficulty: Beginner | Time: 15 minutes | Basis: From the README Import MDX or StarDict dictionaries and check selected words beside the page, without an AI account. **Who it is for:** A reader of technical or foreign-language books who wants definitions for selected words without leaving the page or going online. **The problem:** Reading stops when a word needs a quick check, and online lookup is unavailable or unwanted. **The outcome:** Selected words show definitions from dictionaries the reader has imported, including original images and audio when the MDX files include them. ### Steps 1. Open 设置 → 自定义字典 (Settings → custom dictionary) and import an MDX or StarDict dictionary you have the rights to use. 2. Name the dictionary and turn it on. 3. Open a book and select a word in the text. 4. Use 综合查询 (unified query) and choose which dictionaries to search, if you want more than one. 5. If you imported an older plain-text dictionary and want its original resources, import it again. ### Prompt to paste into your agent ```text Using the sobranie2406/modureader repo, import the dictionary file into Modu Reader and look up the word . Report the dictionary name and the definition returned, and confirm that the lookup works with no AI account set up. ``` ### Caveat The README says the app does not ship dictionary files, so you must supply your own dictionary and confirm you have the right to use it. Dual-use notice: only use this on software, sites and systems you own or are authorized to test. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/sobranie2406-modureader/look-up-words-with-offline-dictionaries/